English
Related papers

Related papers: NormKD: Normalized Logits for Knowledge Distillati…

200 papers

Knowledge distillation (KD) has become an important technique for model compression and knowledge transfer. In this work, we first perform a comprehensive analysis of the knowledge transferred by different KD methods. We demonstrate that…

Computer Vision and Pattern Recognition · Computer Science 2021-06-07 Fei Ding , Yin Yang , Hongxin Hu , Venkat Krovi , Feng Luo

Knowledge distillation (KD) compresses the network capacity by transferring knowledge from a large (teacher) network to a smaller one (student). It has been mainstream that the teacher directly transfers knowledge to the student with its…

Knowledge distillation is a common paradigm for transferring capabilities from larger models to smaller ones. While traditional distillation methods leverage a probabilistic divergence over the output of the teacher and student models,…

Machine Learning · Computer Science 2025-10-01 Prajjwal Bhattarai , Mohammad Amjad , Dmytro Zhylko , Tuka Alhanai

Existing knowledge distillation methods typically work by imparting the knowledge of output logits or intermediate feature maps from the teacher network to the student network, which is very successful in multi-class single-label learning.…

Machine Learning · Computer Science 2025-06-02 Penghui Yang , Ming-Kun Xie , Chen-Chen Zong , Lei Feng , Gang Niu , Masashi Sugiyama , Sheng-Jun Huang

We address the challenge of producing trustworthy and accurate compact models for edge devices. While Knowledge Distillation (KD) has improved model compression in terms of achieving high accuracy performance, calibration of these compact…

Computer Vision and Pattern Recognition · Computer Science 2024-12-17 Ibtihel Amara , Nazanin Sepahvand , Brett H. Meyer , Warren J. Gross , James J. Clark

Knowledge distillation (KD) is an effective model compression technique that transfers knowledge from a high-performance teacher to a lightweight student, reducing computational and storage costs while maintaining competitive accuracy.…

Computer Vision and Pattern Recognition · Computer Science 2025-11-17 Fengming Yu , Haiwei Pan , Kejia Zhang , Jian Guan , Haiying Jiang

Knowledge distillation is a popular approach for enhancing the performance of ''student'' models, with lower representational capacity, by taking advantage of more powerful ''teacher'' models. Despite its apparent simplicity and widespread…

Machine Learning · Computer Science 2023-12-12 Mher Safaryan , Alexandra Peste , Dan Alistarh

Knowledge distillation (KD) has witnessed its powerful capability in learning compact models in object detection. Previous KD methods for object detection mostly focus on imitating deep features within the imitation regions instead of…

Computer Vision and Pattern Recognition · Computer Science 2022-04-01 Zhaohui Zheng , Rongguang Ye , Ping Wang , Dongwei Ren , Wangmeng Zuo , Qibin Hou , Ming-Ming Cheng

This research note provides a quick introduction to the knowledge distillation loss function used in object classification. In particular, we discuss its connection to a previously proposed logits matching loss function. We further treat…

Machine Learning · Computer Science 2024-08-28 Defang Chen

Existing techniques often attempt to make knowledge transfer from a powerful machine translation (MT) to speech translation (ST) model with some elaborate techniques, which often requires transcription as extra input during training.…

Computation and Language · Computer Science 2023-04-21 Hao Zhang , Nianwen Si , Yaqi Chen , Wenlin Zhang , Xukui Yang , Dan Qu , Zhen Li

Knowledge Distillation (KD) emerges as one of the most promising compression technologies to run advanced deep neural networks on resource-limited devices. In order to train a small network (student) under the guidance of a large network…

Machine Learning · Computer Science 2023-12-15 Yi Guo , Yiqian He , Xiaoyang Li , Haotong Qin , Van Tung Pham , Yang Zhang , Shouda Liu

Knowledge distillation (KD) is a popular method to train efficient networks ("student") with the help of high-capacity networks ("teacher"). Traditional methods use the teacher's soft logits as extra supervision to train the student…

Computer Vision and Pattern Recognition · Computer Science 2021-08-17 Guo-Hua Wang , Yifan Ge , Jianxin Wu

Knowledge distillation is considered a compression mechanism when judged on the resulting student's accuracy and loss, yet its functional impact is poorly understood. We quantify the compression capacity of knowledge distillation and the…

Machine Learning · Computer Science 2026-03-17 Israel Mason-Williams , Gabryel Mason-Williams , Helen Yannakoudakis

Knowledge distillation is a model compression technique in which a compact "student" network is trained to replicate the predictive behavior of a larger "teacher" network. In logit-based knowledge distillation, it has become the de facto…

Machine Learning · Computer Science 2026-05-12 Ejafa Bassam , Dawei Zhu , Kaigui Bian

Knowledge Distillation (KD) is one proposed solution to large model sizes and slow inference speed in semantic segmentation. In our research we identify 25 proposed distillation loss terms from 14 publications in the last 4 years.…

Computer Vision and Pattern Recognition · Computer Science 2023-09-08 Onno Niemann , Christopher Vox , Thorben Werner

Knowledge distillation (KD) has been a predominant method for compressing Large Language Models (LLMs). In this paper, we first revisit KD and Low-Rank Adaption (LoRA) and demonstrate that they follow the same paradigm. Inspired by this…

Computation and Language · Computer Science 2025-02-26 Runming Yang , Taiqiang Wu , Jiahao Wang , Pengfei Hu , Yik-Chung Wu , Ngai Wong , Yujiu Yang

This study proposes a method for knowledge distillation (KD) of fine-tuned Large Language Models (LLMs) into smaller, more efficient, and accurate neural networks. We specifically target the challenge of deploying these models on…

Computation and Language · Computer Science 2024-06-13 Ehsan Latif , Luyang Fang , Ping Ma , Xiaoming Zhai

Traditional knowledge distillation focuses on aligning the student's predicted probabilities with both ground-truth labels and the teacher's predicted probabilities. However, the transition to predicted probabilities from logits would…

Computer Vision and Pattern Recognition · Computer Science 2026-04-08 Penghui Yang , Chen-Chen Zong , Sheng-Jun Huang , Lei Feng , Bo An

Knowledge Distillation (KD) is a model-agnostic technique to improve model quality while having a fixed capacity budget. It is a commonly used technique for model compression, where a larger capacity teacher model with better quality is…

Machine Learning · Computer Science 2021-03-02 Jiaxi Tang , Rakesh Shivanna , Zhe Zhao , Dong Lin , Anima Singh , Ed H. Chi , Sagar Jain

In recent years, large language models (LLMs) have shown exceptional capabilities across various natural language processing (NLP) tasks. However, such impressive performance often comes with the trade-off of an increased parameter size,…

Computation and Language · Computer Science 2025-02-19 Minchong Li , Feng Zhou , Xiaohui Song